Split Learning for collaborative deep learning in healthcare

Abstract

Shortage of labeled data has been holding the surge of deep learning in healthcare back, as sample sizes are often small, patient information cannot be shared openly, and multi-center collaborative studies are a burden to set up. Distributed machine learning methods promise to mitigate these problems. We argue for a split learning based approach and apply this distributed learning method for the first time in the medical field to compare performance against (1) centrally hosted and (2) non collaborative configurations for a range of participants. Two medical deep learning tasks are used to compare split learning to conventional single and multi center approaches: a binary classification problem of a data set of 9000 fundus photos, and multi-label classification problem of a data set of 156,535 chest X-rays. The several distributed learning setups are compared for a range of 1-50 distributed participants. Performance of the split learning configuration remained constant for any number of clients compared to a single center study, showing a marked difference compared to the non collaborative configuration after 2 clients (p < 0.001) for both sets. Our results affirm the benefits of collaborative training of deep neural networks in health care. Our work proves the significant benefit of distributed learning in healthcare, and paves the way for future real-world implementations.

Workshop paper: 8 pages, 2 figures, 1 table

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
• Revisiting Distributed Synchronous SGD
• Experiments on Parallel Training of Deep Neural Network using Model Averaging
• No Peek: A Survey of private distributed deep learning
• Detailed comparison of communication efficiency of split learning and federated learning
• ExpertMatcher: Automating ML Model Selection for Clients using Hidden Representations

Cited by in corpus (16)

• Precision Health Data: Requirements, Challenges and Existing Techniques for Data Security and Privacy
• Overview of AI and Communication for 6G Network: Fundamentals, Challenges, and Future Research Opportunities
• Privacy-preserving Artificial Intelligence Techniques in Biomedicine
• FedCG: Leverage Conditional GAN for Protecting Privacy and Maintaining Competitive Performance in Federated Learning
• Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions
• Decentralized Deep Learning for Multi-Access Edge Computing: A Survey on Communication Efficiency and Trustworthiness
• Similarity-based Label Inference Attack against Training and Inference of Split Learning
• ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection
• Personalized Federated Deep Learning for Pain Estimation From Face Images
• Self-supervised Cross-silo Federated Neural Architecture Search
• Multi-limb Split Learning for Tumor Classification on Vertically Distributed Data
• FedDCT: Federated Learning of Large Convolutional Neural Networks on Resource Constrained Devices using Divide and Collaborative Training
• Splitfed learning without client-side synchronization: Analyzing client-side split network portion size to overall performance
• Constrained Generative Adversarial Network Ensembles for Sharable Synthetic Data Generation
• Spatio-Temporal Split Learning for Autonomous Aerial Surveillance using Urban Air Mobility (UAM) Networks
• SplitVAEs: Decentralized scenario generation from siloed data for stochastic optimization problems